Development and evaluation of AI model with deep learning for segmentation of extraocular muscles in thyroid eye disease

Clinical Snapshot

Key Findings

• P Value: Significant differences noted but specific p-values not provided in abstract

• Effect Size: Improved DSC with larger datasets (52 vs 32 vs 12 cases)

• Primary Outcome: DICE similarity coefficients varied significantly between dataset sizes for inferior and medial rectus muscles

• Nnt Or Sensitivity: Strong correlation between AI and manual SIR measurements across all extraocular muscles

• Confidence Interval: Not reported

Clinical Application

Requires specialized MRI protocols and computational resources; implementation challenges not addressed Could potentially support ophthalmologists and radiologists in TED management, though validation in Australian population needed. No specific PBS or TGA considerations mentioned. Patients with thyroid eye disease requiring orbital imaging assessment

Abstract

PURPOSE: To develop and evaluate an AI model for the segmentation of extraocular muscles (EOMs) using Magnetic Resonance Imaging (MRI). DESIGN: Single-center study with retrospective study. METHODS: The study included 52 patients with thyroid eye disease (TED) who underwent MRI examination of the orbital region at the Department of Ophthalmology, Osaka Metropolitan University, between October 2020 and June 2023. Manual labelling of all EOMs was performed on all slices. An AI model was created and compared with the manually labelled data using 5-fold cross validation on data sets of 12, 32, and 52 cases. The average signal intensity ratio (SIR) within the EOMs was measured. The primary outcome was the comparison of DICE similarity coefficients (DSC) as the agreement rate between AI's result and manual labelling amongst the three data sets (52 cases vs 32 cases vs 12 cases). The secondary outcome was the correlation of SIR between the AI and manual labelling. RESULTS: A significant difference in DSC was observed between the 12-, 32-, and 52-case data sets for the inferior rectus muscle and medial rectus muscle. A significant correlation was observed between the AI and manual labelling for SIR in all EOMs. CONCLUSIONS: An AI model was successfully developed for the automatic segmentation of EOMs. There was little measurement error between AI and manual labelling, and the AI model using 52 cases had improved measurement accuracy compared to the AI models using 32 and 12 cases.

References

1. 1.Haruna, Y., Tagami, M., Kurosaki, R., Nishio, M., Kinari, G., Tomita, M., Misawa, N., Muragaki, Y., & Honda, S. (2026). Development and evaluation of AI model with deep learning for segmentation of extraocular muscles in thyroid eye disease. PLoS One. https://doi.org/10.1371/journal.pone.0349074